CN115326242A - Online performance evaluation and fault diagnosis method and system for power transmission line state monitoring sensor - Google Patents
Online performance evaluation and fault diagnosis method and system for power transmission line state monitoring sensor Download PDFInfo
- Publication number
- CN115326242A CN115326242A CN202211108859.5A CN202211108859A CN115326242A CN 115326242 A CN115326242 A CN 115326242A CN 202211108859 A CN202211108859 A CN 202211108859A CN 115326242 A CN115326242 A CN 115326242A
- Authority
- CN
- China
- Prior art keywords
- sensor
- transmission line
- value
- fault diagnosis
- performance evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 82
- 238000003745 diagnosis Methods 0.000 title claims abstract description 77
- 230000005540 biological transmission Effects 0.000 title claims abstract description 65
- 238000012544 monitoring process Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000005259 measurement Methods 0.000 claims abstract description 52
- 238000013528 artificial neural network Methods 0.000 claims abstract description 36
- 230000008859 change Effects 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000005070 sampling Methods 0.000 claims description 24
- 238000001914 filtration Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims 1
- 230000003252 repetitive effect Effects 0.000 claims 1
- 230000035772 mutation Effects 0.000 description 15
- 238000000354 decomposition reaction Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000032365 Electromagnetic interference Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K15/00—Testing or calibrating of thermometers
- G01K15/007—Testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L25/00—Testing or calibrating of apparatus for measuring force, torque, work, mechanical power, or mechanical efficiency
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/02—Testing or calibrating of apparatus covered by the other groups of this subclass of auxiliary devices, e.g. of instrument transformers according to prescribed transformation ratio, phase angle, or wattage rating
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention provides an online performance evaluation and fault diagnosis method of a power transmission line state monitoring sensor, which comprises the following steps: collecting measurement value data measured by a sensor; preprocessing measured value data measured by a sensor; inputting the pre-processed data of the first m measured values into a neural network to obtain a predicted value of the sensor measurement at the next moment; calculating residual values of the predicted values and the actual measured values corresponding to the predicted values; comparing the residual error value with a set threshold value, and judging that the sensor generates a sudden change signal if the number of times that the residual error value continuously exceeds the threshold value is greater than a set positive integer D; if the residual value does not exceed the threshold, then a repeat uncertainty for the actual measurement is calculated to evaluate data reliability. Correspondingly, the invention also provides an online performance evaluation and fault diagnosis system of the power transmission line state monitoring sensor and a computer readable storage medium.
Description
Technical Field
The present invention relates to a sensor monitoring method and system, and more particularly, to a sensor monitoring method and system for a power transmission line.
Background
The sensor plays an especially important role in the power system as an essential component of the on-line monitoring system of the power transmission line, monitors the operation condition of the power transmission line at every moment and provides basis for further decision making, so that the accuracy of detection information, the timeliness of information transmission and the reliability of operation are very important, and the sensor can effectively monitor and evaluate the operation of the power transmission line only if the sensor operates well, thereby providing accurate and reliable basis for a line operation scheme. Therefore, in the fault diagnosis of the transmission line system, firstly, the sensor should be checked, and the operation state should be effectively monitored and evaluated.
With the wide application of the on-line monitoring system of the power transmission line, the research work of fault evaluation on the power transmission line in the prior art mainly focuses on the evaluation of the monitoring quantity of the power transmission line or the whole monitoring system, and there is only a technology of fault detection and accuracy evaluation on the sensor itself. However, the importance of sensor performance monitoring and evaluation is well understood by those skilled in the art.
Based on this, it is desirable to provide an online performance evaluation and fault diagnosis method for a power transmission line state monitoring sensor.
Disclosure of Invention
One of the purposes of the invention is to provide an online performance evaluation and fault diagnosis method for a power transmission line state monitoring sensor, which aims to realize online evaluation and fault diagnosis of the sensor performance by combining online monitoring measurement uncertainty.
In order to achieve the above object, the present invention provides an online performance evaluation and fault diagnosis method for a power transmission line state monitoring sensor, which comprises the steps of:
(1) Collecting measurement value data measured by a sensor;
(2) Inputting the previous m measured value data into a neural network to obtain a predicted value of the sensor measurement at the next moment;
(3) Calculating residual values of the predicted values and the actual measured values corresponding to the predicted values;
(4) And comparing the residual value with a set threshold value, and judging that the sensor generates a sudden change signal if the number of times that the residual value continuously exceeds the threshold value is greater than a set positive integer D.
The online performance evaluation and fault diagnosis method of the power transmission line state monitoring sensor combines a time series prediction method and a neural network-based intelligent learning method. Since there are usually many electromagnetic interferences and random interferences in the actual measurement environment, so that some noises inevitably exist in the time series measured by the sensor, the sensor data is first preprocessed, and the preprocessed data is used as the input of the neural network.
Further, in the step (4) of the online performance evaluation and fault diagnosis method of the power transmission line state monitoring sensor, if the residual value does not exceed the threshold value, the repeated uncertainty of the actual measurement value is calculated to evaluate the reliability of the data.
Further, in the step (1) of the online performance evaluation and fault diagnosis method of the power transmission line state monitoring sensor, the sensor data is subjected to redundant sampling or normal sampling.
Preferably, in the method for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor, the method further includes, between step (1) and step (2), the steps of: the measured value data measured by the sensor is preprocessed.
Further, in the method for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor, the preprocessing includes wavelet filtering to filter noise and improve data quality.
Further, in the online performance evaluation and fault diagnosis method of the power transmission line state monitoring sensor, the wavelet filtering adopts at least one of Daubechie wavelets, coiflets wavelets, symlets and BiorSolines.
In specific embodiments, daubechie wavelets, coiflets wavelets, symlets, biorSolines, and the like may be used. In addition to selecting the appropriate wavelet, one skilled in the art can determine the appropriate decomposition scale, filtering threshold, as desired. The threshold may be determined using a prior art universal threshold, minimization risk threshold, or hypothesis testing.
The technical scheme completes the nonlinear processing of the wavelet coefficient according to the determined threshold value and completes the filtering processing.
Further, in the step (2) of the online performance evaluation and fault diagnosis method of the power transmission line state monitoring sensor, the neural network includes a BP neural network.
Still further, the BP neural network includes an input layer, a hidden layer, and an output layer.
The BP neural network in the invention adopts a three-layer structure: the system comprises an input layer, a hidden layer and an output layer, wherein the input layer inputs the measurement results at m moments before a sensor, and the output layer only has one node, namely the measurement result at the next moment of the sensor is predicted.
Further, in step (4) of the online performance evaluation and fault diagnosis method for the power transmission line state monitoring sensor, the repeated uncertainty u (y) is calculated according to the following formula:
wherein n represents the number of measurements, k n Representing a coefficient, δ, related to the number of measurements i | max Representing the residual value of a single measurement of the sensor.
Where n =1 for an on-line sensor, when k is present n =0.8。
Further, in the method for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor according to the present invention, when the sensor is determined to generate a sudden change signal, a feature of the sudden change signal is extracted, and whether the sensor has a fault is determined based on the feature of the sudden change signal.
In the technical scheme, when the sensor is judged to generate the mutation signal, the technical scheme extracts the characteristics of the mutation signal based on the frequency band technology of wavelet and wavelet packet transformation, and judges whether the sensor has a fault or not based on the corresponding relation between the characteristics and the mutation reason.
Table 1 shows the correspondence between the characteristics of the mutation signals and the causes of the mutations.
TABLE 1
Cause of mutation | Output signal characteristics of sensor |
Given an input | Only low frequency signals |
Process perturbation | Only low frequency signals |
Sensor therefore | Low frequency signal + high frequency signal |
Controlled object | Input bandwidth to sensor |
Further, in the method for on-line performance evaluation and fault diagnosis of the power transmission line state monitoring sensor, when the characteristics of the mutation signal are low-frequency signal + high-frequency signal, the sensor is judged to have a fault.
Another object of the present invention is to provide an online performance evaluation and fault diagnosis system for a power transmission line state monitoring sensor, which can combine online monitoring measurement uncertainty to realize online evaluation and fault diagnosis of sensor performance.
Based on the above object, the present invention correspondingly provides an online performance evaluation and fault diagnosis system for a power transmission line state monitoring sensor, which comprises:
the data acquisition module is used for acquiring measurement value data measured by the sensor;
the neural network module inputs the previous m measured value data into the neural network module to obtain a predicted value measured by the sensor at the next moment;
an evaluation and diagnosis module that calculates residual values of the predicted values and the actual measured values corresponding thereto; and comparing the residual value with a set threshold value, and judging that the sensor generates a sudden change signal if the number of times that the residual value continuously exceeds the threshold value is greater than a set positive integer D.
Further, in the system for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor according to the present invention, the evaluation and diagnosis module is further configured to: if the residual value does not exceed the threshold, then a repeat uncertainty for the actual measurement is calculated to evaluate data reliability.
Further, in the online performance evaluation and fault diagnosis system of the power transmission line state monitoring sensor, the data acquisition module performs redundant sampling or normal sampling on the sensor data.
Furthermore, the online performance evaluation and fault diagnosis system of the power transmission line state monitoring sensor further comprises a preprocessing module, and the preprocessing module is used for preprocessing measured value data measured by the sensor.
Furthermore, in the system for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor, the preprocessing includes wavelet filtering to filter noise.
Furthermore, in the online performance evaluation and fault diagnosis system of the power transmission line state monitoring sensor, the wavelet filtering adopts at least one of Daubechie wavelets, coiflets wavelets, symlets wavelets and BiorSolines.
Further, in the online performance evaluation and fault diagnosis system of the power transmission line state monitoring sensor of the present invention, the neural network module includes a BP neural network.
Furthermore, in the online performance evaluation and fault diagnosis system of the power transmission line state monitoring sensor, the BP neural network includes an input layer, a hidden layer and an output layer.
Further, in the online performance evaluation and fault diagnosis system of the power transmission line state monitoring sensor of the present invention, the evaluation and diagnosis module calculates the repeated uncertainty u (y) according to the following formula:
wherein,n represents the number of measurements, k n Representing a coefficient, δ, related to the number of measurements i | max Representing the residual value of a single measurement of the sensor.
Further, in the system for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor according to the present invention, when n =1, it indicates that the sensor is an online sensor, and k is the online sensor n =0.8。
Further, in the system for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor according to the present invention, the evaluation and diagnosis module is further configured to: when the sensor is determined to generate the abrupt change signal, the characteristics of the abrupt change signal are extracted, and whether the sensor has failed is determined based on the characteristics of the abrupt change signal.
Further, in the system for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor according to the present invention, the evaluation and diagnosis module is configured to: and when the characteristics of the sudden change signal are a low-frequency signal and a high-frequency signal, judging that the sensor has a fault.
It is a further object of the present invention to provide a computer readable storage medium capable of executing a computer program for enabling online evaluation of sensor performance and fault diagnosis in conjunction with online monitoring of measurement uncertainty.
In view of the above objects, the present invention accordingly provides a computer-readable storage medium having stored thereon a computer program for executing the method for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor according to the present invention.
The online performance evaluation and fault diagnosis method of the power transmission line state monitoring sensor can be used for various power transmission line state monitoring sensors, including temperature, current, tension, vibration, breeze waving sensors and the like.
The online performance evaluation and fault diagnosis method and system of the power transmission line state monitoring sensor and the computer readable storage program have the following beneficial effects:
the method can effectively, accurately and conveniently monitor the accuracy of the detection information of the sensor, the timeliness of the transmission information and the reliability of operation, and provide basis for further decision making, thereby ensuring effective monitoring and evaluation of the operation of the power transmission line and providing accurate and reliable basis for the operation scheme of the line.
Drawings
Fig. 1 is a schematic flow chart of an online performance evaluation and fault diagnosis method for a power transmission line state monitoring sensor according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of an architecture of a neural network used in an embodiment of the method and system for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor according to the present invention.
FIG. 3 illustrates an example of a signal output by a temperature sensor that is normally sampled in one embodiment.
Detailed Description
The method and system for on-line performance evaluation and fault diagnosis of a power transmission line state monitoring sensor according to the present invention will be further explained and explained with reference to the drawings and the specific embodiments of the specification, however, the explanation and explanation do not unduly limit the technical solution of the present invention.
Fig. 1 is a schematic flowchart of an online performance evaluation and fault diagnosis method for a power transmission line state monitoring sensor according to an embodiment of the present invention.
In the implementation mode, the temperature data of the conducting wire acquired by the power transmission line is taken as an example, and the tested sensor is a PT-100 temperature sensor. The measuring range of the sensor is 100 ℃, the temperature sensing element is Cu50, and the nominal precision grade of the sensor is 1 grade. Through tests, the actual repeated uncertainty of the sensor is 0.23 ℃, and the numerical value can be compared with the repeated uncertainty obtained by adopting the technical scheme subsequently, so that the implementation effect of the scheme is verified.
In this embodiment, the online performance evaluation and fault diagnosis of the PT-100 temperature sensor by using the online performance evaluation and fault diagnosis method of the transmission line state monitoring sensor according to the present invention includes the steps of:
100: collecting measured value data measured by a sensor: in the embodiment, redundant sampling is adopted, and the redundant sampling period is set to be 100ms (the frequency is 10Hz which is set for fault diagnosis and real-time filtering by using a redundant sampling frequency method). In other embodiments, the start-up sampling period may be set to 6.4s when sampling normally.
200: wavelet filtering the measured value data measured by the sensor: in the embodiment, db4 wavelets (namely Daubechie wavelets) are adopted, the length of a data window is N =64, the number of decomposition layers is J =4, a filtering threshold is a scale-related threshold generated by a Birge-Massart strategy, and a threshold function is in a soft threshold form.
300: inputting the pre-processed data of the first m measured values into a neural network to obtain a predicted value of the sensor measurement at the next moment: in the present embodiment, since the sampling period of the temperature value is long, the BP neural network of 10 input nodes is selected for prediction.
Fig. 2 shows a schematic diagram of an architecture of a neural network used in an embodiment of the method and system for online performance evaluation and fault diagnosis of a power transmission line state monitoring sensor according to the present invention.
As shown in fig. 2, the BP neural network has a three-layer structure: the system comprises an input layer, a hidden layer and an output layer, wherein the input layer inputs measurement results y (t), y (t-1), \8230, y (t-m + 1) at m moments before the sensor, the output layer only has one node, and the predicted measurement result at the next moment of the sensor is output
400: residual values of the predicted values and the actual measured values corresponding thereto are calculated.
500: comparing the residual error value with a set threshold value, and judging that the sensor generates a sudden change signal if the number of times that the residual error value continuously exceeds the threshold value is greater than a set positive integer D; if the residual value does not exceed the threshold, then a repeat uncertainty of the actual measurement is calculated to assess data reliability. In this embodiment, the threshold θ may be set to 1 ℃.
In this embodiment, the repetition uncertainty u (y) is calculated according to the following formula:
wherein n represents the number of measurements, k n Representing a coefficient, δ, related to the number of measurements i | max Representing the residual value of a single measurement of the sensor.
Where n =1 for an on-line sensor, when k is present n =0.8。
When the sensor is determined to generate the abrupt change signal, the abrupt change signal identification program extracts the characteristics of the abrupt change signal based on the band technique of wavelet and wavelet packet transform, and determines whether the sensor has a failure based on the characteristics of the abrupt change signal.
In one embodiment, the online performance evaluation and fault diagnosis system of the power transmission line state monitoring sensor is adopted to perform online performance evaluation and fault diagnosis on the PT-100 temperature sensor. The online performance evaluation and fault diagnosis system comprises: the device comprises a data acquisition module, a neural network module and an evaluation and diagnosis module.
The data acquisition module acquires measurement value data measured by the sensor. For example, in some embodiments, redundant sampling may be used, with a redundant sampling period of 100ms (at 10Hz, which is provided for fault diagnosis and real-time filtering using the redundant sampling frequency method). In other specific embodiments, the start-sampling period may be set to 6.4s when sampling normally.
The neural network module is used for obtaining a predicted value of the sensor measurement at the next moment based on the previous m measured value data input into the neural network module. In some specific embodiments, a BP neural network of 10 input nodes is selected for prediction due to the longer sampling period of the temperature values.
In some specific embodiments, a BP neural network as shown in FIG. 2 may be employed. The BP neural network adopts a three-layer structure: input layer, hidden layer andthe output layer inputs the measurement results y (t), y (t-1), 8230, y (t-m + 1) at m moments before the sensor, has only one node, and outputs the predicted measurement result at the next moment of the sensor
In the online performance evaluation and fault diagnosis system, an evaluation and diagnosis module is used for calculating residual values of predicted values and actual measured values corresponding to the predicted values; the evaluation and diagnosis module compares the residual value with a set threshold value, and judges that the sensor generates a sudden change signal if the number of times that the residual value continuously exceeds the threshold value is greater than a set positive integer D; if the residual value does not exceed the threshold, then a repeat uncertainty of the actual measurement is calculated to assess data reliability. In some specific embodiments, the threshold θ may be set to 1 ℃.
It should be noted that, as a preferred embodiment, the online performance evaluation and fault diagnosis system may further include a preprocessing module, which preprocesses the measured value data measured by the sensor and then inputs the preprocessed measured value data of the first m into the downstream neural network module. In some embodiments, the pre-processing may include wavelet filtering. In some specific embodiments, db4 wavelet (i.e., daubechie wavelet) may be used, the data window length N =64, the number of decomposition layers J =4, the filtering threshold may be a scale-dependent threshold generated by a large-Massart strategy, and the threshold function is in the form of a soft threshold.
It is further noted that, in some embodiments, the evaluation and diagnostic module can calculate the repeat uncertainty u (y) according to the following equation:
wherein n represents the number of measurements, k n Representing a coefficient relating to the number of measurements, | δ i | max Representing the residual value of a single measurement of the sensor.
Where n =1 for an on-line sensor, when k is present n =0.8。
When the sensor is judged to generate the mutation signal, the mutation signal identification program extracts the characteristics of the mutation signal based on the band technology of wavelet and wavelet packet transformation, and the evaluation and diagnosis module judges whether the sensor has a fault based on the characteristics of the mutation signal.
The present invention also provides an embodiment in which a computer program is stored in a computer-readable storage medium, the computer program performing the steps of:
100: the data of the measured values measured by the sensors are collected, for example, by using redundant sampling, and the period of the redundant sampling is set to be 100ms (the frequency is 10Hz, which is set for fault diagnosis and real-time filtering by using a redundant sampling frequency method). Or in other embodiments, the start-up sampling period may be set to 6.4s when sampling normally.
200: wavelet filtering the measured value data measured by the sensor: for example, in some specific embodiments, a db4 wavelet (i.e., daubechie wavelet) is used, the data window length N =64, the number of decomposition layers J =4, the filtering threshold is a scale-dependent threshold generated by a big-masart strategy, and the threshold function is in the form of a soft threshold.
300: inputting the pre-processed data of the first m measured values into a neural network to obtain a predicted value of the sensor measurement at the next moment: in some specific embodiments, due to the longer sampling period of the temperature value, a BP neural network of 10 input nodes is selected for prediction.
400: residual values of the predicted values and the actual measured values corresponding thereto are calculated.
500: comparing the residual value with a set threshold value, and judging that the sensor generates a sudden change signal if the number of times that the residual value continuously exceeds the threshold value is greater than a set positive integer D; if the residual value does not exceed the threshold, then a repeat uncertainty for the actual measurement is calculated to evaluate data reliability. In this embodiment, the threshold θ may be set to 1 ℃.
In some embodiments, the repeat uncertainty u (y) is calculated according to the following formula:
wherein n represents the number of measurements, k n Representing a coefficient relating to the number of measurements, | δ i | max Representing the residual value of a single measurement of the sensor.
Wherein n =1 for an on-line sensor, when k is present n =0.8。
When the sensor is judged to generate the mutation signal, the mutation signal identification program extracts the characteristics of the mutation signal based on the band technology of wavelet and wavelet packet transformation, and judges whether the sensor has a fault based on the characteristics of the mutation signal.
FIG. 3 is an exemplary illustration of a signal output by a temperature sensor normally sampled under one embodiment.
This example performed 10 evaluations of the above sensors in succession, each evaluation having a point count of 100 points, and the average repeat uncertainty of the 10 evaluations are shown in table 2.
TABLE 2 average repeat uncertainty of 10 evaluations of temperature sensor
|
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
Degree of repetition uncertainty | 0.216 | 0.217 | 0.218 | 0.217 | 0.213 | 0.213 | 0.210 | 0.207 | 0.206 | 0.207 |
As can be seen from table 2, there is a large dispersion in the repeat uncertainty of a single measurement, but when the average value is used as the repeat uncertainty in one processing period, it is quite close to the actual value of 0.23 listed above, which shows the effectiveness of the online performance evaluation and fault diagnosis method and system of the power transmission line state monitoring sensor according to the present invention.
In addition, the online performance evaluation and fault diagnosis method and system for the power transmission line state monitoring sensor determine the sensor with sudden change of the found signal as the sensor fault, and are consistent with the reality.
It should be noted that a lower value of the calculated repetition uncertainty is indicative of a better reliability of the sensor.
It should be noted that the prior art in the protection scope of the present invention is not limited to the examples given in the present application, and all the prior art which is not inconsistent with the technical scheme of the present invention, including but not limited to the prior patent documents, the prior publications and the like, can be included in the protection scope of the present invention.
In addition, the combination of the features in the present application is not limited to the combination described in the claims of the present application or the combination described in the embodiments, and all the features described in the present application may be freely combined or combined in any manner unless contradictory to each other.
It should also be noted that the above-listed embodiments are only specific embodiments of the present invention. It is apparent that the present invention is not limited to the above embodiments and similar changes or modifications can be easily made by those skilled in the art from the disclosure of the present invention and shall fall within the scope of the present invention.
Claims (25)
1. A method for on-line performance evaluation and fault diagnosis of a power transmission line state monitoring sensor is characterized by comprising the following steps:
(1) Collecting measurement value data measured by a sensor;
(2) Inputting the previous m measured value data into a neural network to obtain a predicted value of the sensor measurement at the next moment;
(3) Calculating residual values of the predicted values and the actual measured values corresponding to the predicted values;
(4) And comparing the residual error value with a set threshold value, and judging that the sensor generates a sudden change signal if the number of times that the residual error value continuously exceeds the threshold value is greater than a set positive integer D.
2. The method according to claim 1, wherein in step (4), if the residual value does not exceed the threshold, the repeated uncertainty of the actual measurement is calculated to evaluate the reliability of the data.
3. The method for on-line performance evaluation and fault diagnosis of transmission line condition monitoring sensors according to claim 1, wherein in step (1), the sensor data is redundantly sampled or normally sampled.
4. The method for on-line performance evaluation and fault diagnosis of electric transmission line state monitoring sensor according to claim 1, characterized by further comprising the steps between step (1) and step (2): the measured value data measured by the sensor is preprocessed.
5. The method of claim 4, wherein the preprocessing comprises wavelet filtering to filter noise.
6. The method of claim 5, wherein the wavelet filtering is at least one of Daubechie wavelet, coiflets wavelet, symlets wavelet and BiorSolines.
7. The method for on-line performance evaluation and fault diagnosis of electric transmission line condition monitoring sensors according to claim 1, wherein in step (2), the neural network comprises a BP neural network.
8. The method of claim 7, wherein the BP neural network comprises an input layer, a hidden layer and an output layer.
9. The method of claim 2, wherein the evaluation and diagnosis module calculates the repeated uncertainty u (y) according to the following formula:
wherein n represents the number of measurements, k n Representing a coefficient, δ, related to the number of measurements i | max Representing the residual value of a single measurement of the sensor.
10. The method of claim 9, wherein when n =1, the sensor is an online sensor, and k is the time k n =0.8。
11. The method according to claim 1, wherein when the sensor is determined to generate the abrupt change signal, the characteristics of the abrupt change signal are extracted, and whether the sensor has a fault is determined based on the characteristics of the abrupt change signal.
12. The method according to claim 11, wherein it is determined that the sensor has failed when the abrupt change signal is characterized by a low frequency signal + a high frequency signal.
13. An online performance evaluation and fault diagnosis system of a transmission line state monitoring sensor is characterized by comprising:
the data acquisition module is used for acquiring measured value data measured by the sensor;
the neural network module is used for inputting the previous m measured value data into the neural network module so as to obtain a predicted value measured by the sensor at the next moment;
the evaluation and diagnosis module is used for calculating residual values of the predicted values and the actual measured values corresponding to the predicted values; and comparing the residual value with a set threshold value, and judging that the sensor generates a sudden change signal if the number of times that the residual value continuously exceeds the threshold value is greater than a set positive integer D.
14. The system of claim 13, wherein the evaluation and diagnostic module is further configured to: if the residual value does not exceed the threshold, then a repeat uncertainty for the actual measurement is calculated to evaluate data reliability.
15. The system of claim 13, wherein the data collection module performs redundant sampling or normal sampling of the sensor data.
16. The system of claim 13, further comprising a preprocessing module that preprocesses the measurement data from the sensors.
17. The system of claim 16, wherein the preprocessing comprises wavelet filtering to filter out noise.
18. The system of claim 17, wherein the wavelet filtering is at least one of Daubechie wavelets, coiflets wavelets, symlets and BiorSolines.
19. The system of claim 13, wherein the neural network module comprises a BP neural network.
20. The system of claim 19, wherein the BP neural network comprises an input layer, a hidden layer, and an output layer.
21. The system for on-line performance evaluation and fault diagnosis of transmission line condition monitoring sensors according to claim 14, wherein in step (4), the repetitive uncertainty u (y) is calculated according to the following formula:
wherein n represents the number of measurements, k n Representing a coefficient relating to the number of measurements, | δ i | max Representing the residual value of a single measurement of the sensor.
22. The system for on-line performance evaluation and fault diagnosis of transmission line condition monitoring sensors of claim 13, wherein when n =1, it indicates that the sensor is an on-line sensor, and k is the time k n =0.8。
23. The system for online performance assessment and fault diagnosis of an electric transmission line condition monitoring sensor according to claim 13, wherein the assessment and diagnosis module is further configured to: when the sensor is determined to generate the abrupt change signal, the characteristics of the abrupt change signal are extracted, and whether the sensor has failed is determined based on the characteristics of the abrupt change signal.
24. The system for on-line performance evaluation and fault diagnosis of electric transmission line condition monitoring sensors according to claim 23, wherein said evaluation and diagnosis module is configured to: and when the characteristics of the sudden change signal are a low-frequency signal and a high-frequency signal, judging that the sensor has a fault.
25. A computer-readable storage medium on which a computer program is stored, characterized in that the computer program executes the method for online performance evaluation and fault diagnosis of a transmission line condition monitoring sensor according to any one of claims 1 to 12.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211108859.5A CN115326242A (en) | 2022-09-13 | 2022-09-13 | Online performance evaluation and fault diagnosis method and system for power transmission line state monitoring sensor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211108859.5A CN115326242A (en) | 2022-09-13 | 2022-09-13 | Online performance evaluation and fault diagnosis method and system for power transmission line state monitoring sensor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115326242A true CN115326242A (en) | 2022-11-11 |
Family
ID=83930768
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211108859.5A Pending CN115326242A (en) | 2022-09-13 | 2022-09-13 | Online performance evaluation and fault diagnosis method and system for power transmission line state monitoring sensor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115326242A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117553840A (en) * | 2024-01-11 | 2024-02-13 | 深圳汉光电子技术有限公司 | Instrument based on intelligent management and system thereof |
-
2022
- 2022-09-13 CN CN202211108859.5A patent/CN115326242A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117553840A (en) * | 2024-01-11 | 2024-02-13 | 深圳汉光电子技术有限公司 | Instrument based on intelligent management and system thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109186813B (en) | Temperature sensor self-checking device and method | |
CN111460392B (en) | Magnetic suspension train and suspension system fault detection method and system thereof | |
KR101891175B1 (en) | Safety evaluation method for structure using modified dynamaic characteristics | |
JP2006105142A (en) | Fault detection method for device and fault detection/separation system | |
CN111337767B (en) | Fault analysis method for resonant wave speed reducer | |
CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
CN110717472B (en) | Fault diagnosis method and system based on improved wavelet threshold denoising | |
CN115326242A (en) | Online performance evaluation and fault diagnosis method and system for power transmission line state monitoring sensor | |
CN117668684B (en) | Power grid electric energy data anomaly detection method based on big data analysis | |
US12045047B2 (en) | Fault diagnostics systems and methods | |
JP2008108250A (en) | Abnormality detection system for movable body and abnormality detection method for movable body | |
CN114372344B (en) | Quantitative identification method for subsynchronous oscillation damping characteristic influence factors | |
CN115081331A (en) | Wind turbine generator running state abnormity detection method based on state parameter reconstruction error | |
CN114881157A (en) | Method, device and equipment for detecting working state of converter valve and storage medium | |
CN114595721A (en) | Vehicle part strain load prediction method based on road condition recognition | |
CN116627116B (en) | Process industry fault positioning method and system and electronic equipment | |
CN117491813A (en) | Insulation abnormality detection method for power battery system of new energy automobile | |
CN116641941A (en) | Hydraulic system early fault dynamic detection method based on typical variable analysis | |
CN112114215A (en) | Transformer aging evaluation method and system based on error back propagation algorithm | |
CN112816122B (en) | Bolt tightness degree monitoring method based on deep learning and piezoelectric active sensing | |
Yanez-Borjas et al. | Methodology based on statistical features and linear discriminant analysis for damage detection in a truss-type bridge | |
CN115358294A (en) | Micro fault detection method for high-speed train traction system | |
CN114266013A (en) | Deep learning virtual perception network-based transmission system vibration decoupling method | |
Dai et al. | Bearing fault diagnosis based on reinforcement learning and kurtosis | |
Hiranaka et al. | VAE Deviation for Detecting Bearing Anomalies |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |